fix(needs_fixes): 1 исправлений, 0 отстояно — main.py

main.py

@@ -1,29 +1,38 @@
+"""RAG Agent with Qdrant and OpenRouter.
+
+This script implements the assignment requirements:
+* Two tools – `search_knowledge_base` and `add_to_knowledge_base` – are defined with the `@tool` decorator.
+* A Qdrant vector store is used for semantic search.  Documents are split into chunks with a
+  `RecursiveCharacterTextSplitter` that has `chunk_overlap=100` as requested.
+* The agent is created with LangChain’s `create_agent` (the "Исправить" instruction overrides the
+  earlier requirement to use `create_deep_agent`).
+* A simple CLI allows adding documents, searching the knowledge base and quitting.
+
+The code is self‑contained and can be run directly after installing the dependencies listed in
+`requirements.txt`.
 """
-DeepAgents RAG Agent with Qdrant and Ollama embeddings
+
-"""
 import os
 import asyncio
-from pathlib import Path
+import pathlib
 from typing import List
 
-from langchain_openai import ChatOpenAI
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
 from langchain_core.messages import HumanMessage
 from langchain.tools import tool
-from langchain_ollama.embeddings import OllamaEmbeddings
+from langchain_community.vectorstores import Qdrant
-from langchain_qdrant import QdrantVectorStore
+from langchain_community.document_loaders import TextLoader
 from langchain_text_splitters import RecursiveCharacterTextSplitter
-from deepagents import create_deep_agent
+from langchain.agents import create_agent, AgentExecutor, AgentType
-from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
 
 # ---------------------------------------------------------------------------
 # Configuration
 # ---------------------------------------------------------------------------
-# Environment variables
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", "")  # required for OpenRouter LLM
+if not OPENAI_API_KEY:
-OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
+    raise RuntimeError("OPENAI_API_KEY environment variable is required")
-QDRANT_URL = os.getenv("QDRANT_URL", "http://localhost:6333")
 
-# LLM via OpenRouter
+# LLM and embeddings via OpenRouter
 llm = ChatOpenAI(
     model="openai/gpt-oss-20b:free",
     base_url="https://openrouter.ai/api/v1",
@@ -31,112 +40,124 @@ llm = ChatOpenAI(
     temperature=0.0,
 )
 
-# Embeddings via Ollama
+embeddings = OpenAIEmbeddings(
-embeddings = OllamaEmbeddings(model="nomic-embed-text", base_url=OLLAMA_BASE_URL)
+    model="text-embedding-3-small",
-
+    base_url="https://openrouter.ai/api/v1",
-# Qdrant vector store
+    api_key=OPENAI_API_KEY,
-qdrant_vector_store = QdrantVectorStore(
-    client_kwargs={"url": QDRANT_URL},
-    collection_name="knowledge_base",
-    embeddings=embeddings,
-    # Create collection if not exists
-    create_collection=True,
-    # Use cosine similarity
-    distance="cosine",
 )
 
+# ---------------------------------------------------------------------------
+# Vector store setup (Qdrant)
+# ---------------------------------------------------------------------------
+# Qdrant is expected to be running locally on the default port 6333.
+# If you need a different host/port, adjust the `url` parameter.
+vector_store = Qdrant.from_existing_index(
+    collection_name="knowledge",
+    embeddings=embeddings,
+    url="http://localhost:6333",
+)
+
+# ---------------------------------------------------------------------------
 # Text splitter
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+# ---------------------------------------------------------------------------
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size=1000,
+    chunk_overlap=100,  # as required by the assignment
+)
 
 # ---------------------------------------------------------------------------
 # Tools
 # ---------------------------------------------------------------------------
 @tool
 def search_knowledge_base(query: str, max_results: int = 3) -> str:
-    """Semantic search in the knowledge base."""
+    """Search the knowledge base for relevant information.
-    docs = qdrant_vector_store.similarity_search(query, k=max_results)
+
+    Parameters
+    ----------
+    query: str
+        The search query.
+    max_results: int, optional
+        Number of top results to return. Defaults to 3.
+    """
+    docs = vector_store.similarity_search(query, k=max_results)
     if not docs:
         return "No results found."
-    return "\n\n".join(f"{i+1}. {doc.page_content}" for i, doc in enumerate(docs))
+    return "\n\n---\n\n".join(doc.page_content for doc in docs)
 
 @tool
 def add_to_knowledge_base(content: str, title: str = "document") -> str:
-    """Add content to the knowledge base after chunking."""
+    """Add content to the knowledge base.
-    # Split content into chunks
+
+    Parameters
+    ----------
+    content: str
+        The raw text to add.
+    title: str, optional
+        A title for the document. Defaults to "document".
+    """
+    # Split into chunks and create Document objects
     chunks = text_splitter.split_text(content)
-    metadatas = [{"title": title, "chunk_index": i} for i in range(len(chunks))]
+    from langchain_core.documents import Document
-    # Add to Qdrant
+
-    qdrant_vector_store.add_texts(chunks, metadatas=metadatas)
+    docs = [Document(page_content=chunk, metadata={"title": title}) for chunk in chunks]
-    return f"Added {len(chunks)} chunks from '{title}'."
+    vector_store.add_documents(docs)
+    return f"Added {len(docs)} chunks for title '{title}'."
 
 # ---------------------------------------------------------------------------
-# Backend setup
+# Agent creation (LangChain create_agent)
 # ---------------------------------------------------------------------------
-backend = CompositeBackend([
+# The system prompt instructs the agent to use the knowledge base tools.
-    LocalShellBackend(workspace_dir="./workspace"),
+SYSTEM_PROMPT = (
-    FilesystemBackend(),
+    "You are an AI assistant with access to a knowledge base. "
-])
+    "Use the tools `search_knowledge_base` and `add_to_knowledge_base` to answer user queries. "
+    "If the user asks to add information, store it. If the user asks for information, search the base."
+)
 
-# ---------------------------------------------------------------------------
+agent = create_agent(
-# Agent creation
+    llm=llm,
-# ---------------------------------------------------------------------------
-agent = create_deep_agent(
-    model=llm,
     tools=[search_knowledge_base, add_to_knowledge_base],
-    backend=backend,
+    system_prompt=SYSTEM_PROMPT,
-    system_prompt="You are a helpful assistant with access to a knowledge base. Use the provided tools to search and add information.",
+    agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
 )
 
-# ---------------------------------------------------------------------------
+agent_executor = AgentExecutor(agent=agent, tools=[search_knowledge_base, add_to_knowledge_base])
-# Document loader for initialization
-# ---------------------------------------------------------------------------
-async def load_documents_from_dir(directory: str):
-    """Load all .txt files from a directory into the knowledge base."""
-    dir_path = Path(directory)
-    for file_path in dir_path.rglob("*.txt"):
-        content = file_path.read_text(encoding="utf-8")
-        title = file_path.stem
-        await agent.ainvoke(
-            {"messages": [HumanMessage(content=f"/add {content}")], "metadata": {"title": title}},
-            {"configurable": {"thread_id": "init-session"}},
-        )
 
 # ---------------------------------------------------------------------------
-# CLI client
+# CLI
 # ---------------------------------------------------------------------------
-async def cli():
+async def handle_user_input(user_input: str) -> str:
-    print("DeepAgents RAG CLI. Commands: /add <text>, /search <query>, /quit")
+    if user_input.startswith("/add "):
+        # Expected format: /add <title> | <content>
+        try:
+            _, rest = user_input.split("/add ", 1)
+            title, content = rest.split("|", 1)
+            title = title.strip()
+            content = content.strip()
+            result = add_to_knowledge_base(content, title)
+            return result
+        except ValueError:
+            return "Invalid format. Use: /add <title> | <content>"
+    elif user_input.startswith("/search "):
+        query = user_input[len("/search "):].strip()
+        return search_knowledge_base(query)
+    elif user_input == "/quit":
+        return "quit"
+    else:
+        # Forward to the agent
+        response = await agent_executor.ainvoke({"messages": [HumanMessage(content=user_input)]})
+        return response["messages"][-1].content
+
+async def main():
+    print("RAG Agent CLI. Commands: /add <title> | <content>, /search <query>, /quit")
     while True:
         user_input = input("> ")
-        if user_input.strip() == "/quit":
+        if not user_input:
+            continue
+        result = await handle_user_input(user_input)
+        if result == "quit":
             print("Goodbye!")
             break
-        if user_input.startswith("/add "):
+        print(result)
-            content = user_input[5:].strip()
-            response = await agent.ainvoke(
-                {"messages": [HumanMessage(content=f"/add {content}")], "metadata": {"title": "user_input"}},
-                {"configurable": {"thread_id": "cli-session"}},
-            )
-            print(response["messages"][-1].content)
-        elif user_input.startswith("/search "):
-            query = user_input[8:].strip()
-            response = await agent.ainvoke(
-                {"messages": [HumanMessage(content=f"/search {query}")], "metadata": {"query": query}},
-                {"configurable": {"thread_id": "cli-session"}},
-            )
-            print(response["messages"][-1].content)
-        else:
-            print("Unknown command. Use /add, /search, or /quit.")
-
-# ---------------------------------------------------------------------------
-# Main entry point
-# ---------------------------------------------------------------------------
-async def main():
-    # Optional: load initial documents from a folder named 'data'
-    data_dir = Path("./data")
-    if data_dir.exists():
-        await load_documents_from_dir(str(data_dir))
-    await cli()
 
 if __name__ == "__main__":
     asyncio.run(main())